© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18157
    Prev
    Next
    INDEX
    Explanations

    Firefox, Canc, Hill, Missouri entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogi
    -0.07
    bito
    -0.07
    byname
    -0.07
    ubile
    -0.07
     ës
    -0.07
    CLUD
    -0.07
     mili
    -0.07
    æĥ¯äºĨ
    -0.07
    ztat
    -0.07
    opo
    -0.07
    POSITIVE LOGITS
    对æѤ
    0.10
    ãģ«ãģĬãģijãĤĭ
    0.09
    ìĹIJìĦľìĿĺ
    0.09
    ä¸ŃçļĦ
    0.09
    ä¸ŃçļĦæķ°æį®
    0.09
    ä¸Ńå°±
    0.08
    ä¸Ń对
    0.08
    éĩĮçļĦ
    0.08
    è¿Ļè¾¹çļĦ
    0.08
    ä¸Ńä¹ĭ
    0.08
    Activations Density 0.776%

    No Known Activations